Indoor Localization Based on Floor Plans and Power Maps

Abstract

An indoor localization algorithm that is based on fingerprinting and trilateration is developed. The algorithm assumes a priori knowledge of the layout of the environment and the position of the transmitters. First, a power map is simulated around “strategically” sampled training points. Then, the power map is used to produce an initial estimate for the position of the receiver, from which the total losses due to obstacles in the environment are calculated. These losses are extracted from the received power, transforming the non line-of-sight environment to a virtual line-of-sight one. The position of the receiver is finally obtained from the distances estimated from the corrected power by an extended Kalman filter. Numerical simulations and experimental results are presented to evaluate the performance of the proposed algorithm.